cs.AI updates on arXiv.org 6小时前
Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文介绍了LLM Analyzer系统,通过交互式可视化及反事实分析,解决现有LLMs可解释性AI方法的局限,强调人机交互在解释过程中的重要性。

arXiv:2405.00708v2 Announce Type: replace-cross Abstract: Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often computationally inefficient and misaligned with human reasoning processes. Moreover, these methods often treat explanation as a one-time output, overlooking its inherently interactive and iterative nature. In this paper, we present LLM Analyzer, an interactive visualization system that addresses these limitations by enabling intuitive and efficient exploration of LLM behaviors through counterfactual analysis. Our system features a novel algorithm that generates fluent and semantically meaningful counterfactuals via targeted removal and replacement operations at user-defined levels of granularity. These counterfactuals are used to compute feature attribution scores, which are then integrated with concrete examples in a table-based visualization, supporting dynamic analysis of model behavior. A user study with LLM practitioners and interviews with experts demonstrate the system's usability and effectiveness, emphasizing the importance of involving humans in the explanation process as active participants rather than passive recipients.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

LLM分析 可解释AI 交互式可视化
相关文章